2 posts tagged with "agent"

We are introducing the AI Orchestrator — a new worker that runs an AI agent inside your workflow. Instead of wiring every step by hand, you select the workers the agent may use and describe the task. The orchestrator chooses the parameters, calls the workers, adapts when data is missing, and writes the final answer.

It is the difference between a fixed pipeline and a delegation.

Why we built it​

Financial workflows rarely follow the same path twice. A market brief may need price data, news, and the economic calendar — but sometimes the news feed is empty, the calendar needs a wider window, or a symbol has no recent candles. A fixed workflow has to anticipate every branch. The AI Orchestrator can decide at runtime.

Common examples:

• prepare a morning market brief from several sources,
• compare price action with news and macro events,
• monitor a setup and alert only when a score is high enough,
• research a symbol with multiple data providers,
• remember preferences and lessons between scheduled runs.

How it works​

The orchestrator is a ReAct-style tool-calling agent:

1. It receives your prompt, the selected workers, and the run context.
2. Each selected worker is exposed as a tool with its parameter schema.
3. The model reasons, calls a worker, observes the result, and decides the next step.
4. It can retry with different parameters or choose another worker.
5. When it has enough information, it writes the final answer.

Every tool call is a real worker execution. That means API credits, rate limits, credentials, and side effects apply exactly as they would for a normal node. The trace is returned in the calls field so you can audit what happened.

What you get​

The node returns more than a text answer:

The output panel shows answer as its own group next to the calls and workers_used tables, so you can inspect both the result and the path that produced it.

Quick start​

1. Add the node​

Place AI Orchestrator after a trigger and before whatever consumes the result:

[Schedule] -> [AI Orchestrator] -> [Telegram]

2. Select the workers it may use​

Keep the set small and focused. For a market brief:

fetch_price
fetch_news
browse_calendar

Triggers and visualization/widget nodes are hidden automatically — they cannot be executed as tools. The orchestrator itself and parameter_loop are also excluded.

3. Write the prompt​

State the goal, output format, time range, and what to do when data is missing:

Prepare a concise EURUSD market brief for the London session.

Use the last 24 hours of price action, the most relevant news, and the
high-impact events in the next 48 hours. Compare the technical picture with
the news flow and call out disagreements.

Return three bullet points of evidence, a directional bias, and a confidence
score from 1 to 5 on a final line exactly like: SCORE: 4

If news is unavailable, say so explicitly and continue with price and calendar
data. Do not invent headlines.

4. Run it​

Run the workflow from the editor or wait for the trigger. Open the calls trace to see which workers were used and with which parameters.

Memory that lasts between runs​

Set memoryScope to control persistence:

• run — memory only inside the current run (default),
• workflow — session history and long-term facts persist for this workflow/node/owner,
• none — no memory is loaded or saved.

With workflow scope, the agent can use remember and recall tools. Save stable knowledge, not market snapshots:

• good: "Use the London timezone and report prices in EUR for this workflow."
• good: "The CoinGlass funding-rate endpoint is the preferred BTC derivatives source."
• not useful: "BTC is 86,500 right now."

Guardrails for production​

Long-running agents need limits. Open advancedSettings to tune:

• maxSteps — maximum reasoning/tool steps (default 15),
• maxRuntimeSeconds — wall-clock budget for the node (default 180),
• toolTimeout — maximum time for one delegated worker,
• tokenBudget — total token budget, 0 for unlimited,
• maxToolCalls — hard cap on worker invocations, 0 for unlimited,
• planningMode — react to act immediately, plan to write a plan first.

Identical worker calls with identical parameters are cached within a run. A retry with different parameters is a new call and counts against maxToolCalls.

Conditional alerts with a score​

The orchestrator does not decide which downstream nodes run. For deterministic branching, ask for a score and use a Condition node.

Prompt ending:

End with a line exactly like: SCORE: 4

Condition expression:

vars['Orchestrator']['score'] >= 4

Then send Telegram only on the true branch. You get the agent's reasoning plus a hard threshold you can audit.

Choosing between the orchestrator and a fixed pipeline​

Use the AI Orchestrator when the sequence of steps depends on what the data says. Use ordinary workers or Run Workflow when the sequence is known in advance.

A useful rule:

• Fixed steps -> normal workflow nodes.
• Deterministic workflow-to-workflow orchestration -> Run Workflow.
• Adaptive research across several workers -> AI Orchestrator.
• Trading analysis with structured orders -> AI Makler.

Learn more​

The full worker reference — parameters, output fields, memory details, examples, and troubleshooting — is available in the AI Orchestrator documentation.

The deep dive article covers the agent loop, tool selection, prompt engineering, and production patterns in more detail.

Availability​

AI Orchestrator is available now in the public worker library under the AI category. Add it to a workflow, select a few workers, and give it a task.

As always, validate automated outputs before acting on them. The orchestrator is a reasoning layer, not a guarantee of accuracy, and it should sit behind your risk controls.

This post is for educational purposes only and does not constitute investment advice. Financial markets involve risk. Always test workflows and use appropriate risk management.

Markets move fast, and making sense of them requires not just data but context — what happened yesterday, what decisions you made, how conditions have changed. The AI Makler worker brings that context to life: an intelligent financial agent that remembers past sessions, makes decisions, manages positions, and can even trigger other workflows.

Think of it as a tireless trading assistant that keeps notes on every session and gets smarter the more you use it.

What Is AI Makler?​

AI Makler (Polish for "broker") is an AI-powered financial agent that lives in the AI category of the left sidebar. Unlike stateless AI workers that process one request at a time, AI Makler remembers its past analyses, decisions, and market observations across multiple runs within the same workflow.

This makes it ideal for:

• Continuous market monitoring — the agent knows what it saw yesterday
• Trading signal generation — it tracks its own accuracy over time
• Portfolio management — it remembers open positions and reviews them
• Multi-step workflows — it can trigger other workflows based on analysis

Key Features​

🧠 Persistent Memory​

• One MongoDB document per workflow — all runs share the same memory
• Remembers: market state, analysis, orders, triggered workflows
• Configurable history (1–100 iterations, default 20)
• No raw prompts saved — just the meaningful context and decisions

📊 Two Processing Modes​

📈 Structured Orders​

When the agent decides to trade, it returns proper order objects:

{
  "action": "buy",
  "symbol": "BTCUSD",
  "entry_price": 86500.00,
  "target_price": 92000.00,
  "stop_loss": 84000.00,
  "position_size": 0.5,
  "order_type": "market",
  "reason": "Bullish flag breakout on above-average volume",
  "certainty_pct": 82
}

The agent only generates orders when certainty > 60%. If it's not confident, it just returns analysis — no false signals.

🔗 Workflow Orchestration​

AI Makler can trigger other workflows to perform complex tasks. List the allowed workflow IDs in the configuration, and the agent will decide when to run them, passing data along. Triggered runs are fire-and-forget via the same Redis queue as manual runs.

💼 Position Management​

Pass your current open positions as a JSON array, and the agent will review each one — deciding whether to close, hold, or modify based on current market conditions.

How to Use It​

Adding the Worker​

1. Drag AI Makler from the AI category onto your canvas
2. Connect it after your data sources (or trigger it on a schedule)
3. Configure the parameters

Configuration​

Output Fields​

Use Cases​

1. Market Monitor With Memory​

[Schedule Trigger] → [Fetch Market Data] → [AI Makler: analysis] → [Condition: alert?] → [Telegram Notify]

AI Makler runs every hour, sees how conditions evolved, and sends alerts when patterns change.

2. Signal Generator With Position Tracking​

[Schedule] → [Fetch Data + News] → [AI Makler: decision] → [Save Orders to User List]

Agent analyses market data and news, returns buy/sell signals with targets and stop-losses.

3. Portfolio Manager​

[Trigger] → [Fetch Positions + Market Data] → [AI Makler: decision] → [Run Workflow "Execute Orders"]

Agent receives current open positions, reviews each one, and decides what to do. The execution workflow handles the actual order placement.

4. Multi-Strategy Coordinator​

[Trigger] → [AI Makler: analysis]
         → [Trigger: Run Backtest Workflow]
         → [Trigger: Run Risk Analysis Workflow]

Agent decides which analysis workflows to run based on market conditions, passing relevant data to each.

Memory in Action​

When AI Makler runs for the first time, it has clean memory. After each session, it saves:

• What the market looked like
• What analysis it produced
• What orders it generated
• What workflows it triggered

On the next run, it gets a summary of previous sessions:

PREVIOUS SESSIONS (most recent first):
  [1] 2026-06-21T08:00:00 | BTCUSD: Bullish, ETHUSD: Neutral | Orders: 2
  [2] 2026-06-20T20:00:00 | BTCUSD: Ranging, high volume | Orders: 1 | Triggered: 1
  [3] 2026-06-20T12:00:00 | BTCUSD: Bearish rejection at 88k

This context lets the agent spot trends in its own decision-making and adapt.

Legal Disclaimer​

This is not financial advice. Trading involves substantial risk of financial loss. The AI Makler worker is a tool for analysis and automation — all trading decisions should be reviewed by a qualified professional. Past performance in memory does not guarantee future results.